Obsidian MCP Server Enhanced
@labeveryday
Obsidian MCP Server Enhanced について
This project provides a Model Context Protocol (MCP) server for interacting with Obsidian vaults through AI assistants.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-obsidian-enhanced": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}ツール
8Get content of a note from your Obsidian vault
Create a new note in your Obsidian vault
Update an existing note in your Obsidian vault
Append content to an existing note
Delete a note from your Obsidian vault
List files and folders in your Obsidian vault
Get the currently active file in Obsidian
Create a daily note with predefined sections
概要
What is Obsidian MCP Server Enhanced?
A Model Context Protocol (MCP) server that integrates Amazon Q with Obsidian vaults, allowing Amazon Q to interact with notes, search, and manage vault content without requiring the Obsidian application to be open. It uses the Obsidian Local REST API plugin for all operations and is built with FastMCP.
How to use Obsidian MCP Server Enhanced?
Install by cloning the repository, creating a Python virtual environment, and installing dependencies with pip install -e ".[dev]". Configure a .env file with OBSIDIAN_API_KEY, OBSIDIAN_HOST, and OBSIDIAN_PORT. Integrate with Amazon Q CLI by adding an MCP server entry in ~/.aws/amazonq/mcp.json pointing to run_server.py. Run the server with python run_server.py.
Key features of Obsidian MCP Server Enhanced
- Read, create, update, append, and delete notes in Obsidian
- List files and folders in your vault
- Search notes via basic search functionality
- Create daily notes with predefined sections
- Create meeting notes with structured templates
Use cases of Obsidian MCP Server Enhanced
- Automate note creation and management through Amazon Q commands
- Search and retrieve notes from your vault without opening Obsidian
- Generate daily or meeting notes with consistent structure using AI
- Integrate an AI assistant into your knowledge management workflow
- Perform bulk operations on notes via Amazon Q's natural language interface
FAQ from Obsidian MCP Server Enhanced
What are the prerequisites to use this server?
You need Obsidian installed with a vault, the Local REST API plugin enabled and configured, and Python 3.10 or newer.
How do I configure the server for my vault?
Set the environment variables OBSIDIAN_API_KEY, OBSIDIAN_HOST (default 127.0.0.1), OBSIDIAN_PORT (default 27124) in a .env file. Additional options include OBSIDIAN_PROTOCOL, OBSIDIAN_VERIFY_SSL, and OBSIDIAN_TIMEOUT.
How does it integrate with Amazon Q?
Add an MCP server definition in ~/.aws/amazonq/mcp.json with the command uv and arguments pointing to the repository directory and run_server.py. Amazon Q can then invoke the server’s tools.
What tools are currently available?
Implemented tools include obsidian_read_note, obsidian_create_note, obsidian_update_note, obsidian_append_note, obsidian_delete_note, obsidian_list_files, obsidian_get_active_file, and obsidian_create_daily_note. Additional tools like obsidian_search are planned for Phase 2.
Is the project feature‑complete?
Phase 1 (core infrastructure and basic file/search/daily‑note operations) is complete. Phase 2 (advanced search, metadata management, note organization, search‑and‑compile) is planned.
「メモリとナレッジ」の他のコンテンツ
Zettelkasten MCP Server
entanglrA Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.
MCP server for Obsidian
MarkusPfundsteinMCP server that interacts with Obsidian via the Obsidian rest API community plugin
Notion MCP Integration
danhilseA simple MCP integration that allows Claude to read and manage a personal Notion todo list
Docs MCP Server
araboldGrounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools
RAG Documentation MCP Server
hannesrudolphAn MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.
コメント